Yeah, that's a massive problem with the natural language domain all across machine learning.

Unfortunately it's very difficult to track down training data for chess commentary in the first place, let alone trim down biases. For reference, I was able to gather about 1 million samples, but it really needs a billion.

Hopefully through data augmentation and better general intelligence models we can make better progress on bias issues soon, as that's a huge problem when we start trusting AI models too much in life.

You might be able to kludge a fix to tokenize the output and replace he/him/she/her with them/their. It's not as sexy as the engine outputting the correct words, but it should get the job done.

Yes, in this case as long as they still agree when it actually names people, I don't think it would be too difficult. There may be factors I'm not considering though.

Harder would be more general models like GPT-2 and GPT-3.

Singular "they" doesn't care about the gender of the person named, so it should be good.

Appreciate the honesty here. Pretty wild how natural this model feels with 1 million samples.

Sometimes it seems really accurate (like the cherry-picked GIF in the overview docs) and sometimes really off.

I think for the most part, it knows more than it lets on, but finding the right sampling methods (or better yet, generalized search) to generate the best comments is a tough problem because it's difficult to evaluate quality.

There's some info on the sampling methods here: https://chrisbutner.github.io/ChessCoach/high-level-explanat...

What makes it unfortunate that it used masculine pronouns? If it had used purely female pronouns would that make you feel better?

Probably not. The issue with always using one set of pronouns is that people with other pronouns may feel isolated. For example, always assuming software devs are male could cause female devs to feel like they don't belong.

Realistically, it's really hard to fix this encoded bias in language models.

It does. Thanks for expressing this.

Yeah it’s always annoyingly jarring when people assume that. You can even see in the comments on this topic that people attack the suggestion of gender neutral language, which further compounds on the feeling like we don’t belong or are explicitly unwanted.

There are certain people whose disapproval is a badge of honor. They show up in threads like this.

Would 'queen' be considered masculine or feminine? Bishops? Knights (joan of arc excepted)? Are pawns slaves? Ahhh, the sport of kings, reduced to 2021.

Unsure how any of those are relevant? I pointed out the descriptions of the current player being trained - a pretty important part of this project.

Personal attacks aren't cool and will get you banned here. Please review the rules and please don't post that way to HN. We're trying for a quite different quality of conversation here.

https://news.ycombinator.com/newsguidelines.html

Not really, no. Singular "they" is pretty much everywhere now, despite some people's best efforts.

It seems delusional to think there are many instituional efforts that try to prevent singular "they".

I'm talking to several individuals in this very thread

It seems like you are the only one in this thread who cares so much about pronouns to put effort into using them.